Mingqi Gao

Track-Anything. Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Awesome-Video-Object-Segmentation. 🔥 Latest advances in Video Object Segmentation (VOS) – papers, datasets, and projects.

sam-body4d. 🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.

VOS-Review. Datasets and Papers (with codes) discussed in "Deep Learning for Video Object Segmentation: A Review", Artificial Intelligence Review, 2023.

FACM. [ICIP 2016] A MATLAB implementation of the texture segmentation method in paper: "A factorization based active contour model for texture segmentation", IEEE International Conference on Image Processing (ICIP 2016).

Chan-Vese-model. A MATLAB implementation of Chan-Vese model for image segmentation, using the idea proposed by Chan and Vese.

DMFormer. [IEEE T-CSVT] Decoupled Multimodal Transformers (DMFormer) for Referring Video Object Segmentation

YoURVOS. YouTube Untrimmed Referring Video Object Segmentation

NNforMNIST. A 3-layer Fully Connected Neural Network for MNIST Classification, implemented using Python 3.5 and Numpy.